Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mhylle/claude-skills-collection --skill codebase-auditgit clone --depth 1 https://github.com/mhylle/claude-skills-collectionWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mhylle/claude-skills-collection/codebase-audit)<a href="https://agentmods.dev/skills/mhylle/claude-skills-collection/codebase-audit"><img src="https://agentmods.dev/badge/skills/mhylle/claude-skills-collection/codebase-audit.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.03273 |
| Opus 5 | $0.00000 | $0.01636 |
| Sonnet 5 | $0.00000 | $0.00655 |
| Haiku 4.5 | $0.00000 | $0.00327 |
Grade A, and why
codebase-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 225 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Codebase Audit
Long-running comprehensive adversarial audit. Orchestrates per-partition reviews through /adversarial-reviewer --codebase, then synthesizes findings into a written report. Designed for methodical full coverage, not strategic sampling — use when the user wants the whole thing reviewed and is willing to spend the tokens and time.
Positioning
| Skill | What it does | Coverage | Output | When |
|---|---|---|---|---|
/code-review |
Per-phase quality gate | Changed files | Verdict + notes | During implementation |
/adversarial-reviewer (diff) |
Hostile pre-merge review | Changed files | BLOCK/CONCERNS/CLEAN | Before a merge |
/adversarial-reviewer --codebase |
Adversarial sample of repo | 5-10 files per persona | HIGH/MEDIUM/LOW-RISK + most-concerning area | Quick whole-repo sanity check |
/codebase-audit |
Methodical full audit | Every partition | Written report + risk register | Onboarding / due diligence / tech-debt review |
/code-quality-audit |
Metrics: coverage, complexity, cycles, mutation | Whole repo (metric-based) | Numeric gate | Quantitative health |
Pair codebase-audit with code-quality-audit for a complete picture: this skill gives you the qualitative adversarial read; code-quality-audit gives you the quantitative one.
Usage
/codebase-audit # Audit CWD
/codebase-audit src/ # Scope to a subtree
/codebase-audit --resume # Pick up from last checkpoint
/codebase-audit --only api # Re-run a specific partition
/codebase-audit --force # Ignore existing partition reports (re-review everything)
Expect 200K-500K tokens and 30-60 minutes of wall clock for a typical ~500-file repo. This is a deliberate investment. Confirm with the user before kicking off if the cost would surprise them.
Workflow
Step 1: Scope and map
Determine the scope root (path argument, or CWD). Build the map:
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 225 lines · 0 tokens per session scan A ba2707559a63
codebase-audit is a skill published in the GitHub repository mhylle/claude-skills-collection (18 stars, last pushed 5d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,273 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
autoreview
Pre-commit/ship code review: Codex default; optional Claude or Pi.
rework-rate
Measure and interpret PR rework rate — the emerging 5th DORA metric.
omh-code-review
This is a Hermes-native code-review workflow skill.
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
code-reviewer
Code review specialist focused on patterns, bugs, security, and performance.
agent-teams-simplify-and-harden
Implementation + audit loop using parallel agent teams with structured simplify, harden, and document passes. Spawns implementation agents to do the work, then audit agents to find complexity, security gaps, and spec deviations, then loops until code compiles cleanly, all tests pass, and auditors find zero issues or…